GoCardless MCP Server
Enables AI assistants to interact with GoCardless payment data, providing tools to manage customers, payments, mandates, subscriptions, and payouts. Includes Xero integration support for automatic parsing of metadata.
README
GoCardless MCP Server
A Model Context Protocol (MCP) server for GoCardless API integration, enabling AI assistants to interact with GoCardless payment data.
Features
This MCP server provides tools to:
- Customers: List, get, and create customers
- Payments: List, get, and create payments
- Mandates: List and get mandates
- Subscriptions: List and get subscriptions (including combined details with customer/mandate)
- Payouts: List payouts
- Xero Integration: Automatic detection and parsing of Xero contact/invoice/payment IDs from metadata
Limitations
- Read-only recommended: While customer and payment creation are supported, read-only API tokens are recommended for most use cases
- No update operations: Existing records cannot be modified
- No cancellation: Subscriptions, mandates, and payments cannot be cancelled through this server
Installation
Using uvx (Recommended for Claude Code/Cursor)
No installation required - uvx will automatically fetch and run the package:
uvx --from git+https://github.com/jmceleney/gocardless-mcp.git gocardless-mcp
Configure in your MCP settings (see configuration examples below).
Using pipx
pipx install git+https://github.com/jmceleney/gocardless-mcp.git
Using pip
pip install git+https://github.com/jmceleney/gocardless-mcp.git
Local Development
# Clone the repository
git clone https://github.com/jmceleney/gocardless-mcp.git
cd gocardless-mcp
# Install in development mode
pip install -e .
Configuration
Environment Variables
You'll need to configure these environment variables:
GOCARDLESS_ACCESS_TOKEN(required): Your GoCardless API access tokenGOCARDLESS_ENVIRONMENT(optional): Eithersandboxorlive(defaults tosandbox)
Get a GoCardless Access Token:
- Sign up for a GoCardless sandbox account
- Navigate to Developers > API tokens
- Create a new access token
- Copy the token for use in configuration
Setup for Different AI Tools
Claude Desktop
Claude Desktop is the easiest way to get started with MCP servers.
Configuration file location:
- MacOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%/Claude/claude_desktop_config.json
Add this configuration:
{
"mcpServers": {
"gocardless": {
"command": "gocardless-mcp",
"env": {
"GOCARDLESS_ACCESS_TOKEN": "your_access_token_here",
"GOCARDLESS_ENVIRONMENT": "sandbox"
}
}
}
}
After configuration:
- Restart Claude Desktop
- Look for the 🔨 (hammer) icon in the bottom-right corner
- Click it to verify the GoCardless server is connected
- Start asking questions like "Show me my recent GoCardless customers"
Claude Code
Claude Code works best with uvx for automatic package management.
Method 1: Using uvx (Recommended)
claude mcp add gocardless \
--env GOCARDLESS_ACCESS_TOKEN=your_token_here \
--env GOCARDLESS_ENVIRONMENT=sandbox \
-- uvx --from git+https://github.com/jmceleney/gocardless-mcp.git gocardless-mcp
Method 2: Edit Configuration File Directly
Edit ~/.claude.json:
{
"mcpServers": {
"gocardless": {
"type": "stdio",
"command": "uvx",
"args": ["--from", "git+https://github.com/jmceleney/gocardless-mcp.git", "gocardless-mcp"],
"env": {
"GOCARDLESS_ACCESS_TOKEN": "your_access_token_here",
"GOCARDLESS_ENVIRONMENT": "sandbox"
}
}
}
}
After configuration:
- Restart Claude Code
- Verify with:
claude mcp list - The GoCardless server should appear in the list
Cursor IDE
Cursor works best with uvx for automatic package management.
Project-specific configuration (recommended):
Create .cursor/mcp.json in your project root:
{
"mcpServers": {
"gocardless": {
"command": "uvx",
"args": ["--from", "git+https://github.com/jmceleney/gocardless-mcp.git", "gocardless-mcp"],
"env": {
"GOCARDLESS_ACCESS_TOKEN": "your_access_token_here",
"GOCARDLESS_ENVIRONMENT": "sandbox"
}
}
}
}
Global configuration (available in all projects):
Create ~/.cursor/mcp.json:
{
"mcpServers": {
"gocardless": {
"command": "uvx",
"args": ["--from", "git+https://github.com/jmceleney/gocardless-mcp.git", "gocardless-mcp"],
"env": {
"GOCARDLESS_ACCESS_TOKEN": "your_access_token_here",
"GOCARDLESS_ENVIRONMENT": "sandbox"
}
}
}
}
After configuration:
- Restart Cursor
- Open the MCP settings page to verify the server is connected
- The Composer Agent will automatically use GoCardless tools when relevant
Other MCP Clients
For any MCP client that supports stdio transport:
# Make sure environment variables are set
export GOCARDLESS_ACCESS_TOKEN="your_token_here"
export GOCARDLESS_ENVIRONMENT="sandbox"
# Run the server
gocardless-mcp
The server communicates via JSON-RPC over stdin/stdout, so it won't produce output when run directly.
Data Hierarchy
GoCardless data follows this hierarchy:
- Customer (CU*) → Mandate (MD*) → Subscription (SB*) / Payment (PM*)
Mandates authorize recurring payments. Subscriptions generate recurring payments automatically.
Available Tools
Customer Tools
list_customers: List all customers (optional limit parameter)get_customer: Get a specific customer by IDcreate_customer: Create a new customer (requires email, optional given_name, family_name, company_name)
Payment Tools
list_payments: List payments (optional limit, status, subscription, mandate filters)get_payment: Get a specific payment by ID (includes links to mandate/subscription)create_payment: Create a new payment (requires amount, currency, mandate_id, optional description)
Mandate Tools
list_mandates: List mandates (optional limit and customer parameters)get_mandate: Get a specific mandate by ID (includes link to customer)
Subscription Tools
list_subscriptions: List subscriptions (optional limit and status parameters)get_subscription: Get a specific subscription by ID (includes link to mandate)get_subscription_details: Get complete subscription info including mandate and customer in one call
Payout Tools
list_payouts: List payouts (optional limit parameter)
Usage Examples
Once configured in Claude Desktop, you can ask:
- "Show me my recent GoCardless customers"
- "Get details for customer CU123"
- "Create a new customer with email test@example.com"
- "List all pending payments"
- "Show me the details of payment PM123"
Development & Testing
Testing with MCP Inspector
The MCP Inspector provides an interactive web interface to test your server:
# Run the inspector (requires Node.js)
npx @modelcontextprotocol/inspector gocardless-mcp
This will:
- Start the inspector on
http://localhost:6274 - Open your browser automatically
- Allow you to set environment variables in the UI
- Interactively test all available tools
In the Inspector:
- Set your
GOCARDLESS_ACCESS_TOKENin the environment variables section - Set
GOCARDLESS_ENVIRONMENTtosandbox - Browse available tools on the left sidebar
- Click any tool to see its schema
- Fill in parameters and click "Run" to test
Testing with a Python Client
Create a test script to programmatically test the server:
import asyncio
import os
from mcp.client.session import ClientSession
from mcp.client.stdio import StdioServerParameters, stdio_client
async def main():
server_params = StdioServerParameters(
command="gocardless-mcp",
env={
"GOCARDLESS_ACCESS_TOKEN": "your_sandbox_token",
"GOCARDLESS_ENVIRONMENT": "sandbox"
}
)
async with stdio_client(server_params) as (read, write):
async with ClientSession(read, write) as session:
await session.initialize()
# List available tools
tools = await session.list_tools()
print("Available tools:")
for tool in tools.tools:
print(f" - {tool.name}: {tool.description}")
# Test a tool
result = await session.call_tool("list_customers", {"limit": 5})
print("\nResult:", result)
asyncio.run(main())
Running Tests
# Install development dependencies
pip install -e ".[dev]"
# Run tests (when implemented)
pytest
License
MIT
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。